Systems and methods for constructing a three-dimensional model from two-dimensional images

Abstract

A system includes one or more processors coupled to a non-transitory memory, where the one or more processors are configured to generate, using a training set comprising one or more two-dimensional (2D) training images of a dental arch and a three-dimensional (3D) dental arch model, a machine-learning model configured to generate 3D models of dental arches from 2D images of the dental arches, receive one or more 2D images of a dental arch of a user obtained by a user device of the user, and execute the machine-learning model using the one or more 2D images as input to generate a 3D model of the dental arch of the user.

What is claimed is: 
     
       1. A system comprising:
 one or more processors coupled to a non-transitory memory, the one or more processors configured to:
 generate, using a training set comprising one or more two-dimensional (2D) training images of a dental arch and a three-dimensional (3D) dental arch model, a machine-learning model configured to generate 3D models of dental arches from 2D images of the dental arches, wherein generating the machine-learning model comprises:
 (i) determining a number of iterations for training the machine-learning model using the training set; and 
 (ii) training, based on the number of iterations, parameters of the machine-learning model using the training set; 
 
 receive one or more 2D images of a dental arch of a user obtained by a user device of the user; and 
 execute the machine-learning model using the one or more 2D images as input to generate a 3D model of the dental arch of the user. 
 
 
     
     
       2. The system of  claim 1 , wherein the machine-learning model is an optimization model. 
     
     
       3. The system of  claim 1 , wherein the 2D training images include the one or more 2D images of the dental arch of the user obtained by the user device of the user. 
     
     
       4. The system of  claim 1 , wherein the 3D dental arch model is a template 3D dental arch model based on data from a data source that stores a plurality of images and 3D models. 
     
     
       5. The system of  claim 1 , wherein the 3D dental arch model is generated using a prior 3D model associated with the user. 
     
     
       6. The system of  claim 1 , wherein the one or more processors are further configured to iteratively estimate a pose of the 3D dental arch model based on the one or more two-dimensional training images. 
     
     
       7. The system of  claim 1 , wherein the one or more processors are further configured to generate the machine-learning model by performing operations comprising:
 calculating one or more correlation points between the one or more 2D training images and the 3D dental arch model; and 
 generating the machine-learning model further based on the one or more correlation points. 
 
     
     
       8. The system of  claim 1 , wherein the one or more processors are further configured to estimate respective positions of one or more teeth of the 3D model based on the one or more 2D images. 
     
     
       9. The system of  claim 1 , wherein the one or more processors are further configured to generate the 3D dental arch model by removing a 3D representation of at least a portion of a gingiva from an initial 3D dental arch model. 
     
     
       10. The system of  claim 1 , wherein the one or more processors are further configured to:
 generate a user interface that renders the 3D model of the dental arch of the user at the user device; and 
 transmit, to the user device, the user interface for presentation. 
 
     
     
       11. The system of  claim 1 , wherein the 3D dental arch model includes color data, and the one or more processors are further configured to train the machine-learning model to generate color corresponding to the dental arch of the user. 
     
     
       12. The system of  claim 1 , wherein the one or more processors are further configured to transmit the 3D model of the dental arch of the user to a manufacturing system configured to manufacture a dental aligner based on the 3D model. 
     
     
       13. A method comprising:
 generating, by one or more processors coupled to a non-transitory memory, using a training set comprising one or more two-dimensional (2D) training images of a dental arch and a three-dimensional (3D) dental arch model of a dental arch, a machine-learning model configured to generate 3D models of dental arches from 2D images of the dental arches, wherein generating the machine-learning model comprises:
 (i) determining a number of iterations for training the machine-learning model using the training set; and 
 (ii) training, based on the number of iterations, parameters of the machine-learning model using the training set; 
 
 receiving, by the one or more processors, one or more 2D images of a dental arch of a user obtained by a user device of the user; and 
 executing, by the one or more processors, the machine-learning model using the one or more 2D images as input to generate a 3D model of the dental arch of the user. 
 
     
     
       14. The method of  claim 13 , wherein the machine-learning model is an optimization model. 
     
     
       15. The method of  claim 13 , wherein the 2D training images include the one or more 2D images of the dental arch of the user obtained by the user device of the user. 
     
     
       16. The method of  claim 13 , wherein the 3D dental arch model is a template 3D dental arch model based on data from a data source that stores a plurality of images and 3D models. 
     
     
       17. The method of  claim 13 , wherein the 3D dental arch model is generated using a prior 3D model associated with the user. 
     
     
       18. The method of  claim 13 , further comprising iteratively estimating, by the one or more processors, a pose of the 3D dental arch model based on the one or more two-dimensional training images. 
     
     
       19. The method of  claim 13 , wherein generating the machine-learning model comprises:
 calculating, by the one or more processors, one or more correlation points between the one or more 2D training images and the 3D dental arch model; and 
 generating, by the one or more processors, the machine-learning model further based on the one or more correlation points. 
 
     
     
       20. The method of  claim 13 , further comprising estimating, by the one or more processors, respective positions of one or more teeth of the 3D model based on the one or more 2D images. 
     
     
       21. The method of  claim 13 , further comprising generating, by the one or more processors, the 3D dental arch model by removing a 3D representation of at least a portion of a gingiva from an initial 3D dental arch model. 
     
     
       22. The method of  claim 13 , further comprising:
 generating, by the one or more processors, a user interface that renders the 3D model of the dental arch of the user at the user device; and 
 transmitting, by the one or more processors, to the user device, the user interface for presentation. 
 
     
     
       23. The method of  claim 13 , wherein the 3D dental arch model includes color data, and the method comprises training, by the one or more processors, the machine-learning model to generate color corresponding to the dental arch of the user. 
     
     
       24. The method of  claim 13 , further comprising transmitting, by the one or more processors, the 3D model of the dental arch of the user to a manufacturing system configured to manufacture a dental aligner based on the 3D model. 
     
     
       25. A non-transitory computer readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to:
 generate, using a training set comprising one or more two-dimensional (2D) training images of a dental arch and a three-dimensional (3D) dental arch model of a dental arch, a machine-learning model configured to generate 3D models of dental arches from 2D images of the dental arches, wherein generating the machine-learning model comprises:
 (i) determining a number of iterations for training the machine-learning model using the training set; and 
 (ii) training, based on the number of iterations, parameters of the machine-learning model using the training set; 
 
 receive one or more 2D images of a dental arch of a user obtained by a user device of the user; and 
 execute the machine-learning model using the one or more 2D images as input to generate a 3D model of the dental arch of the user. 
 
     
     
       26. The non-transitory computer readable medium of  claim 25 , wherein the machine-learning model is an optimization model. 
     
     
       27. The non-transitory computer readable medium of  claim 25 , wherein the 2D training images include the one or more 2D images of the dental arch of the user obtained by the user device of the user. 
     
     
       28. The non-transitory computer readable medium of  claim 25 , wherein the 3D dental arch model is a template 3D dental arch model based on data from a data source that stores a plurality of images and 3D models. 
     
     
       29. The non-transitory computer readable medium of  claim 25 , wherein the 3D dental arch model is generated using a prior 3D model associated with the user. 
     
     
       30. The non-transitory computer readable medium of  claim 25 , wherein the user is a patient, wherein the patient is a candidate for or currently undergoing dental aligner treatment to reposition one or more teeth of the patient, and wherein the user device is a smartphone of the patient.